Cognitive-AI-Systems / pogema
POGEMA stands for Partially-Observable Grid Environment for Multiple Agents. This is a grid-based environment that was specifically designed to be flexible, tunable and scalable. It can be tailored to a variety of PO-MAPF settings.
☆208Updated 2 weeks ago
Related projects: ⓘ
- [AAAI-2024] MATS-LP addresses the challenging problem of decentralized lifelong multi-agent pathfinding. The proposed approach utilizes a…☆21Updated 3 weeks ago
- [AAAI-2024] Follower: This study addresses the challenging problem of decentralized lifelong multi-agent pathfinding. The proposed Follow…☆37Updated 3 weeks ago
- "When to Switch" Implementation: Addressing the PO-MAPF challenge with RePlan & EPOM policies. This repo includes search-based re-plannin…☆27Updated 3 weeks ago
- This is an umbrella repository that contains links and information about all the tools and algorithms related to the POGEMA Benchmark.☆15Updated last week
- High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC…☆457Updated 7 months ago
- PPO and PyMARL baseline for Pogema environment☆20Updated this week
- ☆45Updated 5 months ago
- The Hierarchical Intrinsically Motivated Agent (HIMA) is an algorithm that is intended to exhibit an adaptive goal-directed behavior usin…☆37Updated 3 weeks ago
- Data-Driven NetHack Tools: Datasets (30+) and recurrent-baselines (AWAC, BC, CQL, IQL, REM)☆64Updated last year
- Data-Driven NetHack Tools: Datasets (30+) and recurrent-baselines (AWAC, BC, CQL, IQL, REM)☆38Updated last year
- JAX and PZ RL envs + algorithms for swarms of CrazyFlies☆57Updated 3 weeks ago
- PyTorch implementation of some reinforcement learning algorithms: A2C, PPO, Behavioral Cloning from Observation (BCO), GAIL.☆135Updated 2 years ago
- Multi-Objective Reinforcement Learning algorithms implementations.☆277Updated last week
- JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️☆185Updated last month
- A multi-agent reinforcement learning solution to Flatland3 challenge.☆15Updated 7 months ago
- Adaptable tools to make reinforcement learning and evolutionary computation algorithms.☆53Updated 2 years ago
- Additional environments compatible with OpenAI gym☆106Updated last month
- Training code PRIMAL2 - Public Repo☆150Updated 3 months ago
- offical code of paper 'SCRIMP: Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding'☆36Updated last year
- Official Implementation for "In-Context Reinforcement Learning for Variable Action Spaces"☆69Updated 7 months ago
- Multi-objective Gymnasium environments for reinforcement learning☆271Updated last week
- Multi-Robot Warehouse (RWARE): A multi-agent reinforcement learning environment☆56Updated this week
- Stable-Baselines3 (SB3) reinforcement learning tutorial for the Reinforcement Learning Virtual School 2021.☆48Updated last year
- ☆192Updated 7 months ago
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch☆46Updated last year
- ☆14Updated this week
- Implementation of Truncated Quantile Critics method for continuous reinforcement learning. https://bayesgroup.github.io/tqc/☆90Updated 3 years ago
- A collection of MARL benchmarks based on TorchRL☆234Updated last week
- Partially Observable Process Gym☆158Updated 2 months ago
- Official implementation for "Anti-Exploration by Random Network Distillation", ICML 2023☆50Updated last year